Prizes & Awards: British Council ISA: Celebrating Internationalism in Schools  |  Science Innovations: Heart simulations on cellphone   |  National Edu News: Science film production  |  International Edu News: Singapore medical training move  |  Scholarships & Sponsorships: National Scholarships Portal- Single Point Solution for Students, Institutions  |  Education Information: World Population To be 9.7 Bn, India to be Most Populated Nation by 2050  |  Life Inspirations: How Rhodell Kpandyu of Liberia Became a Heavy Equipments Technician  |  Health Monitor: FB Posts Indicator of Mental Health and Diabetes  |  Career News: IBPS RRB 2019 Application Link Activated   |  Life Inspirations: Sushila Sable-From Waste Picker to Ambassador of Climate Change  |  Science Innovations: Killing drug-resistant bacteria  |  Technology Inceptions: Canon EOS 200D II DSLR With Dual Pixel AF  |  Teacher Insights: Exercise activates memory neural networks   |  Management lessons: BPCL Allows Women Chemical Engineers in Night Shift  |  Health Monitor: Increase in Global Alcoholism Raises Global Disease Burden  |  
  • Pallikkutam Magazine
  • Companion Magazine
  • Mentor
  • Smart Board
  • Pallikkutam Publications

August 21, 2017 Monday 09:36:29 PM IST

Speech recognition by MS a new milestone

Technology Inceptions

San Francisco: Microsofts conversational speech recognition system -- designed to accurately recognises the words in a conversation like humans do -- has reached a 5.1 per cent error rate, its lowest so far.

This milestone means that, for the first time, a computer can recognise the words in a conversation as well as a person would.

"Our research team reached that 5.1 per cent error rate with our speech recognition system, a new industry milestone, substantially surpassing the accuracy we achieved last year," Microsoft said in a blog post late on Sunday.

Last year in October, the team from Microsoft Artificial Intelligence and Research reported a speech recognition system that makes the same or fewer errors than professional transcriptionists. The researchers had then reported a word error rate (WER) of 5.9 percent.


"Last year, Microsoft's speech and dialog research group announced a milestone in reaching human parity on the 'Switchboard' conversational speech recognition task, meaning we had created technology that recognised words in a conversation as well as professional human transcribers," said Xuedong Huang, Technical Fellow, Microsoft.

'Switchboard' is a corpus of recorded telephone conversations that the speech research community has used for more than 20 years to benchmark speech recognition systems. 

The task involves transcribing conversations between strangers discussing topics such as sports and politics. The team used "Microsoft Cognitive Toolkit 2.1" (CNTK), the most scalable deep learning software available, for exploring model architectures. 

Additionally, Microsoft's investment in cloud compute infrastructure, specifically Azure GPUs, helped improve the effectiveness and speed.


Reaching human parity with an accuracy on par with humans has been a research goal for the last 25 years. 

"Microsoft's willingness to invest in long-term research is now paying dividends for our customers in products and services such as Cortana, Presentation Translator, and Microsoft Cognitive Services," the post read. "Moving from recognising to understanding speech is the next major frontier for speech technology," the post added.

Comments